Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1545 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.6566. Min Act: -0.1700
Data Index: 6107930 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.5316. Min Act: -0.1700
Data Index: 7527266 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.5316. Min Act: -0.1700
Data Index: 758800 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.5316. Min Act: -0.1700
Data Index: 7527254 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.5316. Min Act: -0.1700
Data Index: 7527255 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.4691. Min Act: -0.1700
Data Index: 5960928 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.4691. Min Act: -0.1700
Data Index: 6107941 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.4066. Min Act: -0.1700
Data Index: 7527264 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3441. Min Act: -0.1700
Data Index: 2900301 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3441. Min Act: -0.1700
Data Index: 277992 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3441. Min Act: -0.1700
Data Index: 7042364 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3441. Min Act: -0.1700
Data Index: 4519487 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3441. Min Act: -0.1700
Data Index: 6504858 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3441. Min Act: -0.1700
Data Index: 4745220 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3129. Min Act: -0.1700
Data Index: 7527268 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3129. Min Act: -0.1700
Data Index: 6504849 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.3129. Min Act: -0.1700
Data Index: 7527262 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.2816. Min Act: -0.1700
Data Index: 3630514 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.2816. Min Act: -0.1700
Data Index: 6910701 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6566. Min Range: -7.6566
Max Act: 7.2816. Min Act: -0.1700
Data Index: 7527263 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19